927 papers
This paper proposes YOLOv10n-FBD, a lightweight cherry tomato maturity detection model that integrates CCFM feature fusion, PSA-BiFormer attention, and a C2f-Dual strategy to achieve high precision (94.3% mAP) and speed (369 FPS) while significantly reducing model size and computational complexity compared to existing methods.
This study proposes an LSTM-based speech recognition system for the low-resource Assamese language, utilizing a self-curated dataset and hybrid acoustic features to achieve 95% accuracy while highlighting the challenges posed by phonetic similarities among vowels.
This paper proposes a visual context-aware and spatial receptive field-based algorithm that integrates residual state-space modeling, guidance vectors, and multi-scale deformable attention to effectively restore Dunhuang murals by addressing local pixel forgetting and insufficient spatial perception, thereby significantly improving restoration quality metrics.
This paper proposes a Deep Cross Neural Network (DCNN) framework that achieves 98.4% accuracy in detecting stealthy Hardware Trojans in FPGA-based VLSI circuits by extracting and correlating structural and functional features, offering a reliable solution that reduces dependency on golden reference models.
This systematic review of 104 studies reveals that digital accessibility research is dominated by automated tools and concentrated in education and government sectors, creating an "evaluation–action gap" where methodological convenience and sectoral bias have displaced user-centered approaches and failed to resolve persistent accessibility barriers over the past decade.
The paper introduces OntoLearner, a modular open-source framework that unifies ontology access, LLM-driven learning pipelines, and standardized benchmarking across 22 domains, revealing that the primary bottleneck in ontology learning is a structural mismatch between model knowledge encoding and ontological organization rather than model capability.
This study proposes a retrieval-augmented large language model approach that transforms unstructured assessment feedback into curriculum-aligned error patterns with high accuracy, enabling teaching teams to reflect on instructional impact and guide targeted curriculum revisions in higher education.
This study evaluates the effectiveness of four leading LLM-based conversational agents as assistive technologies for web navigation, finding that while they demonstrate promising potential to enhance accessibility for diverse user groups by interpreting page structures and guiding interactions, their performance varies significantly across different tools.
This paper introduces HE-CloudML, a privacy-preserving framework that enables secure and efficient deep neural network inference on encrypted cloud data using Homomorphic Encryption, achieving near-plaintext accuracy with significant latency improvements over existing solutions while ensuring robust resistance against various privacy attacks.
This paper introduces WSymBERT, a weighted neuro-symbolic attention model that combines contextual language understanding with structured expert knowledge to achieve highly accurate and interpretable automated prediction of CVSS v3.1 Base metrics, outperforming existing transformer baselines while aligning more closely with expert reasoning.